Non-contact Oxygen Saturation Tracking via RGB Video Signal Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-contact methods for monitoring blood oxygen saturation using photoplethysmographic images face challenges due to confounding factors and noise sources, such as specular reflections and changes in geometrical alignment, making it difficult to obtain reliable measurements.
Innovation Solution
A method utilizing standard RGB video cameras with broadband lighting to track changes in blood oxygen saturation by defining regions of interest, normalizing color channel signals, and calculating the ratio of amplitudes, which is robust to small movements and effective over extended periods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-contact PPGi methods are used to monitor vital signs, then ease of operation is improved, but measurement precision deteriorates due to confounding factors and noise
Solution Approach 1:
The patent divides the skin area into multiple regions of interest (ROIs) and processes signals from each region separately. By segmenting the measurement area and combining results from multiple regions, the system reduces the impact of local confounding factors such as specular reflections and geometric alignment changes, thereby improving measurement precision while maintaining ease of operation.
Solution Approach 2:
The patent combines signals from multiple regions of interest and multiple color channels to produce a composite measurement. By merging data from multiple sources and applying signal processing techniques, the system enhances the signal-to-noise ratio and reduces the influence of individual noise sources, resolving the contradiction between ease of use and measurement accuracy.
2Device complexity
If standard RGB video cameras are used for photoplethysmographic imaging, then device complexity is reduced, but measurement precision deteriorates due to noise and confounding factors
Solution Approach 1:
The patent applies signal processing transformations to the raw video signals, including normalization by baseline components, calculation of amplitude ratios, and frequency domain analysis. By changing the parameters of the signal representation and applying mathematical transformations, the system extracts meaningful physiological information from low-quality camera data, improving measurement precision without increasing device complexity.
Solution Approach 2:
The patent uses standard RGB video cameras to create optical copies of the skin surface and processes these visual signals to derive physiological measurements. By utilizing readily available camera technology and processing the optical information through sophisticated algorithms, the system achieves accurate measurements while keeping device complexity low.
3Measurement precision
If broadband lighting is used with RGB video cameras, then measurement precision is improved for tracking oxygen saturation changes, but reliability deteriorates due to sensitivity to ambient light changes
Solution Approach 1:
The patent employs signal processing techniques that continuously monitor and adapt to changing light conditions. By using feedback mechanisms in the signal processing pipeline, including baseline normalization and ratio calculations, the system compensates for ambient light variations and maintains reliable measurements while achieving high precision in tracking oxygen saturation changes.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately tracks changes in oxygen saturation over time with high accuracy, reducing noise interference and maintaining consistency during prolonged recordings, while not providing absolute measurements.
Implementation Method 1
The rPPG signal is a variation in reflectance of light at certain wavelengths as the volume of blood in the skin capillaries varies with the cardiac cycle
Implementation Method 2
oxygenated haemoglobin and deoxygenated haemoglobin absorb differently at different wavelengths
Data Source
Figure 1~3(b)
Figure 2
Figure 4(a)~4(b)
AI summary
A method of monitoring changes in oxygen saturation of a subject by analysing a three colour channel video image of the exposed skin of the subject. Within each colour channel a normalised signal obtained by dividing the intensity signal by its mean value, and the normalised signals are averaged across plural regions of interest within the exposed skin area image of the subject. Regions of interest are selected on the basis of the signal-to-noise ratios for the heart rate and breathing rate components. A single representative waveform for each colour channel is obtained by signal averaging and the ratio of the amplitudes of the representative waveforms from two different colour channels, e.g. blue and red,is taken. The changes in the ratio of amplitudes is output as a measure of changes in blood oxygen saturation.